LIBRARIES

library(tidyverse)
## ── Attaching packages ───────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0
## ── Conflicts ──────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(lubridate)
## 
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
library(maps)
## 
## Attaching package: 'maps'
## The following object is masked from 'package:purrr':
## 
##     map
library(mapdata)
library(viridis)
## Loading required package: viridisLite
library(wesanderson)
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout

Map of World Confirmed Cases

daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") 
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
    borders("world", colour = NA, fill = "grey70") +
    theme_bw() +
    geom_point(shape = 21, color='pink', fill='pink', alpha = 0.5) +
    labs(title = 'World COVID-19 Confirmed cases',x = '', y = '',
        size="Cases (x1000))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=1.5)
## Warning: Removed 54 rows containing missing values (geom_point).

Map of Continential US Confirmed Cases

daily_report <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-05-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa", "Puerto Rico","Northern Mariana Islands", "Virgin Islands", "Recovered", "Guam", "Grand Princess", "District of Columbia", "Diamond Princess")) %>% 
  filter(Lat > 0)
## Parsed with column specification:
## cols(
##   FIPS = col_character(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
    borders("state", colour = "black", fill = "grey90") +
    theme_bw() +
    geom_point(shape = 21, color='orange', fill='orange', alpha = 0.5) +
    labs(title = 'Confirmed Cases of COVID-19 in the Continential US', x = '', y = '',
        size ="Cases (x1000))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=1.5)

Anisa Dhana Example

daily_report <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-05-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
                  "Puerto Rico","Northern Mariana Islands", 
                  "Virgin Islands", "Recovered", "Guam", "Grand Princess",
                  "District of Columbia", "Diamond Princess")) %>% 
  filter(Lat > 0)
## Parsed with column specification:
## cols(
##   FIPS = col_character(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
    borders("state", colour = "black", fill = "grey90") +
    theme_bw() +
    geom_point(shape = 21, color='purple', fill='purple', alpha = 0.5) +
    labs(title = 'COVID-19 Confirmed Cases in the US', x = '', y = '',
        size="Cases (x1000))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=1.5)

mybreaks <- c(1, 100, 1000, 10000, 10000)
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed)) +
    borders("state", colour = "white", fill = "grey85") +
    geom_point(aes(x=Long, y=Lat, size=Confirmed, color=Confirmed),stroke=F, alpha=0.7) +
    scale_size_continuous(name="Cases", trans="log", range=c(1,7), 
                        breaks=mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-99,999", "50,000+")) +
    scale_color_viridis_c(option="magma",name="Cases",
                        trans="log", breaks=mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-99,999", "50,000+"))  +
# Cleaning up the graph
  
  theme_void() + 
    guides( colour = guide_legend()) +
    labs(title = "Anisa Dhana's lagout for COVID-19 Confirmed Cases in the US'") +
    theme(
      legend.position = "bottom",
      text = element_text(color = "#22211d"),
      plot.background = element_rect(fill = "#ffffff", color = NA), 
      panel.background = element_rect(fill = "#ffffff", color = NA), 
      legend.background = element_rect(fill = "#ffffff", color = NA)
    ) +
    coord_fixed(ratio=1.5)
## Warning: Transformation introduced infinite values in discrete y-axis

## Warning: Transformation introduced infinite values in discrete y-axis
## Warning in sqrt(x): NaNs produced
## Warning: Removed 40 rows containing missing values (geom_point).

Mapping Data to Shapes

daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  group_by(Province_State) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Province_State = tolower(Province_State))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
# load the US map data
us <- map_data("state")

# Join the US map data with daily report
state_join <- left_join(us, daily_report, by = c("region" = "Province_State"))

view(state_join)

Wes Anderson Color Palattes

ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 

  geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
  scale_fill_gradientn(colours = 
                         wes_palette("GrandBudapest1", 100, type = "continuous"),
                         trans = "log10") +
  labs(title = "Confirmed COVID-19 Cases in the Continential US'")

RColorBrewer Color Palattes and Number of Confirmed Cases per US County

library(RColorBrewer)


report_03_27_2020 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  unite(Key, Admin2, Province_State, sep = ".") %>% 
  group_by(Key) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Key = tolower(Key))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
# formatting the map data
us <- map_data("state")
counties <- map_data("county") %>% 
  unite(Key, subregion, region, sep = ".", remove = FALSE)

# joining tibbles
state_join <- left_join(counties, report_03_27_2020, by = c("Key"))

# mapping
ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  borders("state", colour = "black") +
  geom_polygon(data = state_join, aes(fill = Confirmed)) +
  scale_fill_gradientn(colors = brewer.pal(n = 5, name = "OrRd"),
                       breaks = c(1, 10, 100, 1000, 10000, 100000),
                       trans = "log10", na.value = "Light Yellow") +
  ggtitle("Number of Confirmed Cases by US County") +
  theme_bw() 
## Warning: Transformation introduced infinite values in discrete y-axis

Massachusetts Confirmed COVID-19 Cases Mapping

daily_report <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Province_State == "Massachusetts") %>% 
  group_by(Admin2) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Admin2 = tolower(Admin2))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
us <- map_data("state")
ma_us <- subset(us, region == "massachusetts")
counties <- map_data("county")
ma_county <- subset(counties, region == "massachusetts")
state_join <- left_join(ma_county, daily_report, by = c("subregion" = "Admin2"))

# plotting state map
ggplot(data = ma_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "white") +
    scale_fill_gradientn(colors = brewer.pal(n = 5, name = "BrBG"),
                         trans = "log10") +
  labs(title = "Confirmed COVID-19 Cases in Massachusetts'")

Plotly Confirmed Cases in MA

ggplotly(
  ggplot(data = ma_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "grey90") +
    scale_fill_gradientn(colours = 
                         wes_palette("Chevalier1", 100, type = "continuous")) +
  ggtitle("Confirmed COVID-19 Cases in MA") +
  labs(x=NULL, y=NULL) +
  theme(panel.border = element_blank()) +
  theme(panel.background = element_blank()) +
  theme(axis.ticks = element_blank()) +
  theme(axis.text = element_blank()))
## Warning: `group_by_()` is deprecated as of dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

EXERCISE 1

# summarize the counts for each country for 9/26/2020
daily_report_9_26 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>%
  rename(Long = "Long_") %>% 
  select(Country_Region, Long, Lat, Province_State, Confirmed) %>%
  group_by(Country_Region, Long, Lat, Confirmed) %>% 
  summarize(Confirmed = sum(Confirmed))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` regrouping output by 'Country_Region', 'Long', 'Lat' (override with `.groups` argument)
ggplot(daily_report_9_26, aes(x = Long, y = Lat, size = Confirmed/1700)) +
    borders("world", colour = NA, fill = "grey80") +
    theme_bw() +
    geom_point(shape = 23, color='red', fill='red', alpha = 0.4) +
    labs(title = 'Global Confirmed COVID-19 Cases', x = '', y = '',
        size ="Cases (x1700))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=1.5)
## Warning: Removed 46 rows containing missing values (geom_point).

EXERCISE 2

# Update Anisa Dhana's graph layout of the US to 9/26/2020
daily_report_us_9_26 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports_us/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
                  "Puerto Rico","Northern Mariana Islands", 
                  "Virgin Islands", "Recovered", "Guam", "Grand Princess",
                  "District of Columbia", "Diamond Princess"))
## Parsed with column specification:
## cols(
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   FIPS = col_double(),
##   Incident_Rate = col_double(),
##   People_Tested = col_double(),
##   People_Hospitalized = col_logical(),
##   Mortality_Rate = col_double(),
##   UID = col_double(),
##   ISO3 = col_character(),
##   Testing_Rate = col_double(),
##   Hospitalization_Rate = col_logical()
## )
mybreaks <- c(1, 100, 1000, 10000, 10000)
ggplot(daily_report_us_9_26, aes(x = Long, y = Lat, size = Confirmed)) +
    borders("state", colour = "white", fill = "grey90") +
    geom_point(aes(x = Long, y = Lat, size = Confirmed, color = Confirmed), stroke = F, alpha = 0.7) +
    scale_size_continuous(name = "Cases", trans = "log", range = c(1,7), 
                        breaks = mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-49,999", "50,000+")) +
    scale_color_viridis_c(option = "magma",name = "Cases",
                        trans = "log", breaks = mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-49,999", "50,000+"))  +
  theme_void() + 
    guides( colour = guide_legend()) +
    labs(title = "Edited Anisa Dhana's lagout for COVID-19 Confirmed Cases in the US'") +
    theme(
      legend.position = "bottom",
      text = element_text(color = "#22211d"),
      plot.background = element_rect(fill = "#ffffff", color = NA), 
      panel.background = element_rect(fill = "#ffffff", color = NA), 
      legend.background = element_rect(fill = "#ffffff", color = NA)
    ) +
    coord_fixed(ratio=1.5)

# Update Anisa Dhana's graph layout of the US to 9/26/2020 --> filtered from global data
daily_report_filtered_us_9_26 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
                  "Puerto Rico","Northern Mariana Islands", 
                  "Virgin Islands", "Recovered", "Guam", "Grand Princess",
                  "District of Columbia", "Diamond Princess"))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )
mybreaks <- c(1, 100, 1000, 10000, 10000)
ggplot(daily_report_filtered_us_9_26, aes(x = Long, y = Lat, size = Confirmed)) +
    borders("state", colour = "white", fill = "grey90") +
    geom_point(aes(x = Long, y = Lat, size = Confirmed, color = Confirmed), stroke = F, alpha = 0.7) +
    scale_size_continuous(name = "Cases", range = c(1,16), 
                        breaks = mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-49,999", "50,000+")) +
    scale_color_viridis_c(option = "magma", name = "Cases",
                        trans = "log", breaks = mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-49,999", "50,000+"))  +
  theme_void() + 
    guides( colour = guide_legend()) +
    labs(title = "Edited Anisa Dhana's lagout for COVID-19 Confirmed Cases in the US'") +
    theme(
      legend.position = "bottom",
      text = element_text(color = "#22211d"),
      plot.background = element_rect(fill = "#ffffff", color = NA), 
      panel.background = element_rect(fill = "#ffffff", color = NA), 
      legend.background = element_rect(fill = "#ffffff", color = NA)
    ) +
    coord_fixed(ratio=1.5)
## Warning: Transformation introduced infinite values in discrete y-axis
## Warning: Removed 59 rows containing missing values (geom_point).

EXERCISE 3

# Updated Number of Confirmed Cases by US County for 9/26/2020
report_09_26_2020 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  unite(Key, Admin2, Province_State, sep = ".") %>% 
  group_by(Key) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Key = tolower(Key))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
# formatting the map data
us <- map_data("state")
counties <- map_data("county") %>% 
  unite(Key, subregion, region, sep = ".", remove = FALSE)

# joining tibbles
state_join <- left_join(counties, report_09_26_2020, by = c("Key"))

# mapping
ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  borders("state", colour = "black") +
  geom_polygon(data = state_join, aes(fill = Confirmed)) +
  scale_fill_gradientn(colors = brewer.pal(n = 5, name = "RdYlGn"),
                       breaks = c(1, 10, 100, 1000, 10000, 100000),
                       trans = "log10", na.value = "Grey") +
  ggtitle("Number of Confirmed Cases by US County") +
  theme_minimal() 
## Warning: Transformation introduced infinite values in discrete y-axis

EXERCISE 4

# Make an interactive plot of a new state --> Alabama
daily_report <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Province_State == "Alabama") %>% 
  group_by(Admin2) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Admin2 = tolower(Admin2))
## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
us <- map_data("state")
al_us <- subset(us, region == "alabama")
counties <- map_data("county")
al_county <- subset(counties, region == "alabama")
state_join <- left_join(al_county, daily_report, by = c("subregion" = "Admin2")) 

# plot state map
ggplot(data = al_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "white") +
    scale_fill_gradientn(colors = brewer.pal(n = 5, name = "BuPu"),
                         trans = "log10") +
  labs(title = "COVID-19 Confirmed Cases in Alabama'")

ggplotly(
  ggplot(data = al_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
    scale_fill_gradientn(colours = 
                         wes_palette("Moonrise1", 100, type = "continuous")) +
  ggtitle("COVID-19 Cases in AL") +
  labs(x=NULL, y=NULL) +
  theme(panel.border = element_blank()) +
  theme(panel.background = element_blank()) +
  theme(axis.ticks = element_blank()) +
  theme(axis.text = element_blank())
)

EXERCISE 5

# Concise Report